Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1609 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4028. Min Range: -2.4028

Max Act: 2.4028. Min Act: -0.0000

Data Index: 1540805 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 2.4028. Min Range: -2.4028

Max Act: 2.0106. Min Act: -0.0000

Data Index: 1632047 (Python Code)

Max Activating Token Index: 810

Text #2

Max Range: 2.4028. Min Range: -2.4028

Max Act: 2.0087. Min Act: -0.0000

Data Index: 1538032 (Python Code)

Max Activating Token Index: 146

Text #3

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.8473. Min Act: -0.0000

Data Index: 1378610 (Python Code)

Max Activating Token Index: 580

Text #4

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.6674. Min Act: -0.0000

Data Index: 1576738 (Python Code)

Max Activating Token Index: 405

Text #5

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.8393. Min Act: -0.0000

Data Index: 1523469 (Python Code)

Max Activating Token Index: 723

Text #6

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.8203. Min Act: -0.0000

Data Index: 1574946 (Python Code)

Max Activating Token Index: 848

Text #7

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.7132. Min Act: -0.0000

Data Index: 1377819 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.7429. Min Act: -0.0000

Data Index: 1492516 (Python Code)

Max Activating Token Index: 412

Text #9

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.7785. Min Act: -0.0000

Data Index: 1561920 (Python Code)

Max Activating Token Index: 518

Text #10

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.6591. Min Act: -0.0000

Data Index: 1582947 (Python Code)

Max Activating Token Index: 697

Text #11

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.5823. Min Act: -0.0000

Data Index: 1387759 (Python Code)

Max Activating Token Index: 220

Text #12

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.7625. Min Act: -0.0000

Data Index: 1382687 (Python Code)

Max Activating Token Index: 505

Text #13

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.7597. Min Act: -0.0000

Data Index: 1388852 (Python Code)

Max Activating Token Index: 556

Text #14

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.8389. Min Act: -0.0000

Data Index: 1477474 (Python Code)

Max Activating Token Index: 221

Text #15

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.8792. Min Act: -0.0000

Data Index: 1494249 (Python Code)

Max Activating Token Index: 567

Text #16

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1439908 (Python Code)

Max Activating Token Index: 893

Text #17

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.7292. Min Act: -0.0000

Data Index: 1616178 (Python Code)

Max Activating Token Index: 148

Text #18

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.5752. Min Act: -0.0000

Data Index: 1553802 (Python Code)

Max Activating Token Index: 786

Text #19

Max Range: 2.4028. Min Range: -2.4028

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1514869 (Python Code)

Max Activating Token Index: 450